← Back to all news
arXiv Machine Learning By Robert Parker

Generating adversarial inputs for a graph neural network model of AC power flow

Read the original on arXiv Machine Learning →

arXiv:2602. 17975v2 Announce Type: replace Abstract: This work formulates and solves optimization problems to generate input points that yield high errors between a neural network's predicted AC power flow solution and solutions to the AC power flow equations.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Sep 25

Reachability-Based Formal Verification of Graph Neural Networks with Node and Edge Features

The paper extends the neural network verification framework to graph neural networks by introducing GraphStar sets, which model uncertainty over both node and edge features. This allows sound propagation of linear message‑passing operations and ReLU nonlinearities for GCN and GINE layers. Experiments on power system tasks (PF, OPF, CFA) and graph classification benchmarks (ENZYMES, PROTEINS) show that the method, called GNNV, yields tighter robustness guarantees than CORA and provides, for the first time, edge‑aware guarantees for GINE‑based models under joint node and edge perturbations.

By Anne M. Tumlin, Ben Wooding, Zhenxuan Shao, Diego Manzanas Lopez, Tyler Derr, Taylor T. Johnson
benchmarks
More like this →
arXiv Machine Learning
5d ago

AC Power Flow Contingency Analysis Using a Single Deep Neural Network

The paper introduces a method that uses a single deep neural network, trained only on basecase AC power flow data, to predict post-contingency operating states for any single-line outage. It frames this prediction as a fixed-point iteration and provides sufficient convergence conditions, certifying them via semidefinite programming. Numerical experiments on the IEEE 118-bus system show that the certified conditions hold for all tested contingencies and that accurate state estimates are achieved in only a few iterations.

By Md Obaidur Rahman, Junjie Qin, Vassilis Kekatos
More like this →
arXiv Machine Learning
Jul 13

Power Flow Feasibility Assessment Using Variational Graph Autoencoders

arXiv:2607. 09122v1 Announce Type: new Abstract: Data-driven methods, including graph neural networks, have been studied for accelerating power flow calculations in recent years, but very little attention has been paid to the solution feasibility, which can be obtained by traditional solvers.

By Ferran Bohigas-Daranas, Hamid Latif-Martinez, Eduardo Prieto-Araujo, Pere Barlet-Ros, Oriol Gomis-Bellmunt
More like this →